def dataPredictions(X_train, X_test, y_train, y_test):
print("training and testing machine learning model")
print("Shape of training_set - X_train: " + str(X_train.shape) +
", y_train: " + str(y_train.shape))
print("Shape of testing_set - X_test: " + str(X_test.shape) +
", y_test: " + str(y_test.shape))
print("\nLinear regression model ")
print(
"Training without longitude and latitude (no polynomial features) and predicting median_house_value"
)
theta_std, X_train, cost_std = lr.batch_regressionModel(
400, X_train[:, 2:], y_train[:, :], 0.01)
print("Testing with the Training set")
print("Test Values:")
print(X_test[:5, :])
print("Comparing the Results (Original - Prediction)")
print(X_test.shape[1])
test_one = np.ones((X_test.shape[0], X_test.shape[1] - 1))
test_one[:, 1:] = X_test[:, 2:]
print(
str(y_test[:5, :]) + " <===> " +
str(lr.hypothesis(theta_std, test_one[:5, :])))
fig1, axs1 = plt.subplots(1, 1)
fig1.canvas.set_window_title('CaliforniaHousingDataPredictions')
fig1.suptitle("CaliforniaHousing Dataset - prediction cost")
axs1.plot(cost_std)
def testRegNormalEquations():
df = pd.read_csv("testData/ex1data2.txt", delimiter=',', header=None)
X = df.values
theta, X = lr.regularized_normalEquation(X[:, :2], X[:, 2:3], 1)
print("<-------------------->")
print("Testing Regularized Normal Equations on Dataset 1.2")
print("<-------------------->")
print("Theta:")
print(theta)
print("<-------------------->")
print(
"Estimate the price of a 1650 sq-ft, 3 br house using normal equations"
)
estimate = np.matrix([1, 1650, 3])
print("Predicted price of a 1650 sq-ft, 3 br house " +
str(lr.hypothesis(theta, estimate)))
print("<-------------------->")
print()
def testRegularizedLinearRegression():
print("\n\n Testing Regularized Linear Regression:")
df = pd.read_csv("testData/ex1data2.txt", delimiter=',', header=None)
X_clean = df.copy().values
df, mu, sigma = featureScaling(df)
X = df.values
y = X[:, 2:3]
theta, X, cost = lr.regularized_linearRegression(
400, 0.01, 1, X[:, :2], X[:, 2:3])
print("<-------------------->")
print("Reg. linear Regression using Dataset 1.2 and lambda = 1")
print(
"Estimate the price of a 1650 sq-ft, 3 br house using gradient descent"
)
estimate = np.matrix(
[1, (1650 - mu[0]) / sigma[0], (3 - mu[1]) / sigma[1]])
print("Predicted price of a 1650 sq-ft, 3 br house " + str(
removeFeatureScaling(lr.hypothesis(theta, estimate), mu[2],
sigma[2])))
print("")
def testNormalEquations():
df = pd.read_csv("testData/ex1data2.txt", delimiter=',', header=None)
X = df.values
theta, cost = lr.normalEquations_regressionModel(X[:, :2], X[:, 2:3])
print("<-------------------->")
print("Testing Normal Equations on Dataset 1.2")
print("<-------------------->")
print("Theta:")
print(theta)
print("<-------------------->")
print("Cost:")
print(float(cost[0]))
print("<-------------------->")
print(
"Estimate the price of a 1650 sq-ft, 3 br house using normal equations"
)
estimate = np.matrix([1, 1650, 3])
print("Predicted price of a 1650 sq-ft, 3 br house " +
str(lr.hypothesis(theta, estimate)))
print("<-------------------->")
print()
def testLinearRegression():
print("\n\n Testing Linear Regression:")
df = pd.read_csv("testData/ex1data2.txt", delimiter=',', header=None)
X_clean = df.copy().values
print(df.head())
print(df.describe())
df, mu, sigma = featureScaling(df)
X = df.values
y = X[:, 2:3]
theta, X, cost = lr.batch_regressionModel(400, X[:, :2], X[:, 2:3],
0.01)
plotLinearRegression(
X_clean, theta, cost,
removeFeatureScaling(np.min(lr.hypothesis(theta, X)), mu[2],
sigma[2]),
removeFeatureScaling(np.max(lr.hypothesis(theta, X)), mu[2],
sigma[2]),
removeFeatureScaling(np.min(X[:, 1]), mu[0], sigma[0]),
removeFeatureScaling(np.max(X[:, 1]), mu[0], sigma[0]))
print("<-------------------->")
print("Final theta")
print(theta)
print("<-------------------->")
print("Testing for training Example 7,8,9,10")
print(
str(X[6, 0]) + " | " +
str(removeFeatureScaling(X[6, 1], mu[0], sigma[0])) + " | " +
str(removeFeatureScaling(X[6, 2], mu[1], sigma[1])))
print(
str(X[7, 0]) + " | " +
str(removeFeatureScaling(X[7, 1], mu[0], sigma[0])) + " | " +
str(removeFeatureScaling(X[7, 2], mu[1], sigma[1])))
print(
str(X[8, 0]) + " | " +
str(removeFeatureScaling(X[8, 1], mu[0], sigma[0])) + " | " +
str(removeFeatureScaling(X[8, 2], mu[1], sigma[1])))
print(
str(X[9, 0]) + " | " +
str(removeFeatureScaling(X[9, 1], mu[0], sigma[0])) + " | " +
str(removeFeatureScaling(X[9, 2], mu[1], sigma[1])))
print("theta*the Training Examples")
solution_seven = lr.hypothesis(theta, X[6, 0:3])
solution_eight = lr.hypothesis(theta, X[7, 0:3])
solution_nine = lr.hypothesis(theta, X[8, 0:3])
solution_ten = lr.hypothesis(theta, X[9, 0:3])
print("Remove feature Scaling")
print("<> " + str(removeFeatureScaling(y[6], mu[2], sigma[2])) +
" - " +
str(removeFeatureScaling(solution_seven, mu[2], sigma[2])) +
" <>")
print("<> " + str(removeFeatureScaling(y[7], mu[2], sigma[2])) +
" - " +
str(removeFeatureScaling(solution_eight, mu[2], sigma[2])) +
" <>")
print("<> " + str(removeFeatureScaling(y[8], mu[2], sigma[2])) +
" - " +
str(removeFeatureScaling(solution_nine, mu[2], sigma[2])) +
" <>")
print("<> " + str(removeFeatureScaling(y[9], mu[2], sigma[2])) +
" - " +
str(removeFeatureScaling(solution_ten, mu[2], sigma[2])) + " <>")
print("<-------------------->")
print(
"Estimate the price of a 1650 sq-ft, 3 br house using gradient descent"
)
estimate = np.matrix(
[1, (1650 - mu[0]) / sigma[0], (3 - mu[1]) / sigma[1]])
print("Predicted price of a 1650 sq-ft, 3 br house " + str(
removeFeatureScaling(lr.hypothesis(theta, estimate), mu[2],
sigma[2])))
print("<-------------------->")
print("Plotting cost")